© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200335
    Prev
    Next
    INDEX
    Explanations

    foul, hits, barge, bear hug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    W
    0.61
    G
    0.57
    D
    0.53
    L
    0.51
    TG
    0.49
    $
    0.49
    H
    0.49
    Then
    0.47
    ibilities
    0.47
    mak
    0.46
    POSITIVE LOGITS
     реклам
    0.47
    绡
    0.46
     profiled
    0.46
     ridicul
    0.45
     размера
    0.44
     velič
    0.44
     удаления
    0.44
     подхода
    0.43
     је
    0.43
     себе
    0.43
    Activations Density 0.000%

    No Known Activations